docs: add MCP server (#13018)

* docs: add MCP server

* typo fix

www/apps/book/.env.sample

@@ -18,3 +18,4 @@ NEXT_PUBLIC_BASE_PATH=
 NEXT_PUBLIC_GA_ID=
 NEXT_PUBLIC_PROD_BASE_URL=
 NEXT_PUBLIC_INTEGRATION_ID=
+NEXT_MCP_SERVER_URL=

www/apps/book/app/learn/introduction/build-with-llms-ai/page.mdx

@@ -1,4 +1,13 @@
-import { InlineIcon } from "docs-ui"
+import { 
+  InlineIcon,
+  Tabs,
+  TabsContent,
+  TabsContentWrapper,
+  TabsList,
+  TabsTrigger,
+  Button,
+  Link
+} from "docs-ui"
 import { AiAssistent, AiAssistentLuminosity } from "@medusajs/icons"
 
 export const metadata = {
@@ -53,6 +62,61 @@ You can add new lines using the `Shift + Enter` shortcut.
 
 ---
 
+## MCP Remote Server
+
+The Medusa documentation provides a remote Model Context Protocol (MCP) server that allows you to find information from the Medusa documentation right in your IDEs or AI tools, such as Cursor.
+
+Medusa hosts a Streamable HTTP MCP server available at `https://docs.medusajs.com/mcp`. you can add it to AI agents that support connecting to MCP servers.
+
+<Tabs defaultValue="cursor">
+  <TabsList>
+    <TabsTrigger value="cursor">Cursor</TabsTrigger>
+    <TabsTrigger value="vscode">VSCode</TabsTrigger>
+  </TabsList>
+  <TabsContentWrapper className="mt-1">
+    <TabsContent value="cursor">
+
+      <Link href="https://cursor.com/install-mcp?name=medusa&config=eyJ1cmwiOiJodHRwczovL2RvY3MubWVkdXNhanMuY29tL21jcCJ9" target="_blank" rel="noopener noreferrer" variant="content">Click here</Link> to add the Medusa MCP server to Cursor.
+
+      To manually connect to the Medusa MCP server in Cursor, add the following to your `.cursor/mcp.json` file or Cursor settings, as explained in the [Cursor documentation](https://docs.cursor.com/context/model-context-protocol):
+
+```json
+{
+  "mcpServers": {
+    "medusa": {
+      "url": "https://docs.medusajs.com/mcp"
+    }
+  }
+}
+```
+
+      
+    </TabsContent>
+    <TabsContent value="vscode">
+
+      <Link href="https://vscode.dev/redirect/mcp/install?name=medusa&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fdocs.medusajs.com%2Fmcp%22%7D" target="_blank" rel="noopener noreferrer" variant="content">Click here</Link> to add the Medusa MCP server to VSCode.
+
+      To manually connect to the Medusa MCP server in VSCode, add the following to your `.vscode/mcp.json` file in your workspace:
+
+```json
+{
+  "servers": {
+    "medusa": {
+      "type": "http",
+      "url": "https://docs.medusajs.com/mcp"
+    }
+  }
+}
+```
+
+      Learn more in the [VSCode documentation](https://code.visualstudio.com/docs/copilot/chat/mcp-servers).
+
+    </TabsContent>
+  </TabsContentWrapper>
+</Tabs>
+
+---
+
 ## Plain Text Documentation
 
 The Medusa documentation is available in plain text format, which allows LLMs and AI tools to easily parse and understand the content.

www/apps/book/generated/edit-dates.mjs

@@ -122,5 +122,5 @@ export const generatedEditDates = {
   "app/learn/fundamentals/api-routes/override/page.mdx": "2025-05-09T08:01:24.493Z",
   "app/learn/fundamentals/module-links/index/page.mdx": "2025-05-23T07:57:58.958Z",
   "app/learn/fundamentals/module-links/index-module/page.mdx": "2025-06-19T16:02:05.665Z",
-  "app/learn/introduction/build-with-llms-ai/page.mdx": "2025-06-27T12:07:08.147Z"
+  "app/learn/introduction/build-with-llms-ai/page.mdx": "2025-07-22T16:19:11.668Z"
 }

www/apps/book/next.config.mjs

@@ -193,6 +193,12 @@ const nextConfig = {
           destination: `${process.env.NEXT_PUBLIC_CLOUD_URL || "https://localhost:3001"}/cloud/:path*`,
           basePath: false,
         },
+        {
+          source: "/mcp",
+          destination:
+            process.env.NEXT_MCP_SERVER_URL || "https://localhost:3001/mcp",
+          basePath: false,
+        },
       ],
     }
   },

www/apps/book/public/llms-full.txt

@@ -19038,6 +19038,32 @@ You can add new lines using the `Shift + Enter` shortcut.
 
 ***
 
+## MCP Remote Server
+
+The Medusa documentation provides a remote Model Context Protocol (MCP) server that allows you to find information from the Medusa documentation right in your IDEs or AI tools, such as Cursor.
+
+Medusa hosts a Streamable HTTP MCP server available at `https://docs.medusajs.com/mcp`. you can add it to AI agents that support connecting to MCP servers.
+
+### Cursor
+
+<Link href="https://cursor.com/install-mcp?name=medusa&config=eyJ1cmwiOiJodHRwczovL2RvY3MubWVkdXNhanMuY29tL21jcCJ9" target="_blank" rel="noopener noreferrer" variant="content">Click here</Link> to add the Medusa MCP server to Cursor.
+
+To manually connect to the Medusa MCP server in Cursor, add the following to your `.cursor/mcp.json` file or Cursor settings, as explained in the [Cursor documentation](https://docs.cursor.com/context/model-context-protocol):
+
+```json
+{
+  "mcpServers": {
+    "medusa": {
+      "url": "https://docs.medusajs.com/mcp"
+    }
+  }
+}
+```
+
+### VSCode
+
+***
+
 ## Plain Text Documentation
 
 The Medusa documentation is available in plain text format, which allows LLMs and AI tools to easily parse and understand the content.